
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import warnings
warnings.filterwarnings('ignore')


df=pd.read_csv("Apps_data.csv")

df


df.head(10)


df.shape

(10841, 13)


df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 10841 entries, 0 to 10840
Data columns (total 13 columns):
 #   Column          Non-Null Count  Dtype  
---  ------          --------------  -----  
 0   App             10841 non-null  object 
 1   Category        10841 non-null  object 
 2   Rating          9367 non-null   float64
 3   Reviews         10841 non-null  object 
 4   Size            10841 non-null  object 
 5   Installs        10841 non-null  object 
 6   Type            10840 non-null  object 
 7   Price           10841 non-null  object 
 8   Content Rating  10840 non-null  object 
 9   Genres          10841 non-null  object 
 10  Last Updated    10841 non-null  object 
 11  Current Ver     10833 non-null  object 
 12  Android Ver     10838 non-null  object 
dtypes: float64(1), object(12)
memory usage: 1.1+ MB


df.describe()


df.describe(include='object')


mc=df.loc[:, df.columns != 'Rating'].columns
print('The columns that need to be worked upon for model building are')
mc

The columns that need to be worked upon for model building are

Index(['App', 'Category', 'Reviews', 'Size', 'Installs', 'Type', 'Price',
       'Content Rating', 'Genres', 'Last Updated', 'Current Ver',
       'Android Ver'],
      dtype='object')


df.duplicated().sum()

483


df.drop_duplicates(inplace=True)


df['Category'].unique()

array(['ART_AND_DESIGN', 'AUTO_AND_VEHICLES', 'BEAUTY',
       'BOOKS_AND_REFERENCE', 'BUSINESS', 'COMICS', 'COMMUNICATION',
       'DATING', 'EDUCATION', 'ENTERTAINMENT', 'EVENTS', 'FINANCE',
       'FOOD_AND_DRINK', 'HEALTH_AND_FITNESS', 'HOUSE_AND_HOME',
       'LIBRARIES_AND_DEMO', 'LIFESTYLE', 'GAME', 'FAMILY', 'MEDICAL',
       'SOCIAL', 'SHOPPING', 'PHOTOGRAPHY', 'SPORTS', 'TRAVEL_AND_LOCAL',
       'TOOLS', 'PERSONALIZATION', 'PRODUCTIVITY', 'PARENTING', 'WEATHER',
       'VIDEO_PLAYERS', 'NEWS_AND_MAGAZINES', 'MAPS_AND_NAVIGATION',
       '1.9'], dtype=object)


df[df['Category']=='1.9']


df.drop(index=10472,inplace=True)


df['Rating'].isna().sum()

1465


df.isnull().sum()

App                  0
Category             0
Rating            1465
Reviews              0
Size                 0
Installs             0
Type                 1
Price                0
Content Rating       0
Genres               0
Last Updated         0
Current Ver          8
Android Ver          2
dtype: int64


df.dropna(subset='Rating',inplace=True)


df['Rating']

0        4.1
1        3.9
2        4.7
3        4.5
4        4.3
        ... 
10834    4.0
10836    4.5
10837    5.0
10839    4.5
10840    4.5
Name: Rating, Length: 8892, dtype: float64


df=df[df['Category'].isnull()==False]

df


df['Rating_category']=df['Rating'].apply(lambda x:'High' if x > 3.5 else 'Low')


df['Rating_category']

0        High
1        High
2        High
3        High
4        High
         ... 
10834    High
10836    High
10837    High
10839    High
10840    High
Name: Rating_category, Length: 8892, dtype: object


df['Rating_category'].unique()

array(['High', 'Low'], dtype=object)


df['Rating_category'].value_counts()

High    8012
Low      880
Name: Rating_category, dtype: int64


df['Reviews'].dtype

dtype('O')


df['Reviews'].unique()

array(['159', '967', '87510', ..., '603', '1195', '398307'], dtype=object)


df['Reviews']=df['Reviews'].astype('int')


df['Reviews'].dtype

dtype('int32')


import plotly.express as px
px.box(df['Reviews'])


df['Reviews']=np.log1p(df['Reviews'])


px.box(df['Reviews'])


df['Size'].dtype

dtype('O')


df['Size'].unique()

array(['19M', '14M', '8.7M', '25M', '2.8M', '5.6M', '29M', '33M', '3.1M',
       '28M', '12M', '20M', '21M', '37M', '2.7M', '5.5M', '17M', '39M',
       '31M', '4.2M', '23M', '6.0M', '6.1M', '4.6M', '9.2M', '5.2M',
       '11M', '24M', 'Varies with device', '9.4M', '15M', '10M', '1.2M',
       '26M', '8.0M', '7.9M', '56M', '57M', '35M', '54M', '201k', '3.6M',
       '5.7M', '8.6M', '2.4M', '27M', '2.5M', '7.0M', '16M', '3.4M',
       '8.9M', '3.9M', '2.9M', '38M', '32M', '5.4M', '18M', '1.1M',
       '2.2M', '4.5M', '9.8M', '52M', '9.0M', '6.7M', '30M', '2.6M',
       '7.1M', '22M', '6.4M', '3.2M', '8.2M', '4.9M', '9.5M', '5.0M',
       '5.9M', '13M', '73M', '6.8M', '3.5M', '4.0M', '2.3M', '2.1M',
       '42M', '9.1M', '55M', '23k', '7.3M', '6.5M', '1.5M', '7.5M', '51M',
       '41M', '48M', '8.5M', '46M', '8.3M', '4.3M', '4.7M', '3.3M', '40M',
       '7.8M', '8.8M', '6.6M', '5.1M', '61M', '66M', '79k', '8.4M',
       '3.7M', '118k', '44M', '695k', '1.6M', '6.2M', '53M', '1.4M',
       '3.0M', '7.2M', '5.8M', '3.8M', '9.6M', '45M', '63M', '49M', '77M',
       '4.4M', '70M', '9.3M', '8.1M', '36M', '6.9M', '7.4M', '84M', '97M',
       '2.0M', '1.9M', '1.8M', '5.3M', '47M', '556k', '526k', '76M',
       '7.6M', '59M', '9.7M', '78M', '72M', '43M', '7.7M', '6.3M', '334k',
       '93M', '65M', '79M', '100M', '58M', '50M', '68M', '64M', '34M',
       '67M', '60M', '94M', '9.9M', '232k', '99M', '624k', '95M', '8.5k',
       '41k', '292k', '11k', '80M', '1.7M', '10.0M', '74M', '62M', '69M',
       '75M', '98M', '85M', '82M', '96M', '87M', '71M', '86M', '91M',
       '81M', '92M', '83M', '88M', '704k', '862k', '899k', '378k', '4.8M',
       '266k', '375k', '1.3M', '975k', '980k', '4.1M', '89M', '696k',
       '544k', '525k', '920k', '779k', '853k', '720k', '713k', '772k',
       '318k', '58k', '241k', '196k', '857k', '51k', '953k', '865k',
       '251k', '930k', '540k', '313k', '746k', '203k', '26k', '314k',
       '239k', '371k', '220k', '730k', '756k', '91k', '293k', '17k',
       '74k', '14k', '317k', '78k', '924k', '818k', '81k', '939k', '169k',
       '45k', '965k', '90M', '545k', '61k', '283k', '655k', '714k', '93k',
       '872k', '121k', '322k', '976k', '206k', '954k', '444k', '717k',
       '210k', '609k', '308k', '306k', '175k', '350k', '383k', '454k',
       '1.0M', '70k', '812k', '442k', '842k', '417k', '412k', '459k',
       '478k', '335k', '782k', '721k', '430k', '429k', '192k', '460k',
       '728k', '496k', '816k', '414k', '506k', '887k', '613k', '778k',
       '683k', '592k', '186k', '840k', '647k', '373k', '437k', '598k',
       '716k', '585k', '982k', '219k', '55k', '323k', '691k', '511k',
       '951k', '963k', '25k', '554k', '351k', '27k', '82k', '208k',
       '551k', '29k', '103k', '116k', '153k', '209k', '499k', '173k',
       '597k', '809k', '122k', '411k', '400k', '801k', '787k', '50k',
       '643k', '986k', '516k', '837k', '780k', '20k', '498k', '600k',
       '656k', '221k', '228k', '176k', '34k', '259k', '164k', '458k',
       '629k', '28k', '288k', '775k', '785k', '636k', '916k', '994k',
       '309k', '485k', '914k', '903k', '608k', '500k', '54k', '562k',
       '847k', '948k', '811k', '270k', '48k', '523k', '784k', '280k',
       '24k', '892k', '154k', '18k', '33k', '860k', '364k', '387k',
       '626k', '161k', '879k', '39k', '170k', '141k', '160k', '144k',
       '143k', '190k', '376k', '193k', '473k', '246k', '73k', '253k',
       '957k', '420k', '72k', '404k', '470k', '226k', '240k', '89k',
       '234k', '257k', '861k', '467k', '676k', '552k', '582k', '619k'],
      dtype=object)


df['Size']=df['Size'].replace({'M':'*10**6','k':'*10**3','Varies with device':np.nan},regex=True)


df['Size'].unique()

array(['19*10**6', '14*10**6', '8.7*10**6', '25*10**6', '2.8*10**6',
       '5.6*10**6', '29*10**6', '33*10**6', '3.1*10**6', '28*10**6',
       '12*10**6', '20*10**6', '21*10**6', '37*10**6', '2.7*10**6',
       '5.5*10**6', '17*10**6', '39*10**6', '31*10**6', '4.2*10**6',
       '23*10**6', '6.0*10**6', '6.1*10**6', '4.6*10**6', '9.2*10**6',
       '5.2*10**6', '11*10**6', '24*10**6', nan, '9.4*10**6', '15*10**6',
       '10*10**6', '1.2*10**6', '26*10**6', '8.0*10**6', '7.9*10**6',
       '56*10**6', '57*10**6', '35*10**6', '54*10**6', '201*10**3',
       '3.6*10**6', '5.7*10**6', '8.6*10**6', '2.4*10**6', '27*10**6',
       '2.5*10**6', '7.0*10**6', '16*10**6', '3.4*10**6', '8.9*10**6',
       '3.9*10**6', '2.9*10**6', '38*10**6', '32*10**6', '5.4*10**6',
       '18*10**6', '1.1*10**6', '2.2*10**6', '4.5*10**6', '9.8*10**6',
       '52*10**6', '9.0*10**6', '6.7*10**6', '30*10**6', '2.6*10**6',
       '7.1*10**6', '22*10**6', '6.4*10**6', '3.2*10**6', '8.2*10**6',
       '4.9*10**6', '9.5*10**6', '5.0*10**6', '5.9*10**6', '13*10**6',
       '73*10**6', '6.8*10**6', '3.5*10**6', '4.0*10**6', '2.3*10**6',
       '2.1*10**6', '42*10**6', '9.1*10**6', '55*10**6', '23*10**3',
       '7.3*10**6', '6.5*10**6', '1.5*10**6', '7.5*10**6', '51*10**6',
       '41*10**6', '48*10**6', '8.5*10**6', '46*10**6', '8.3*10**6',
       '4.3*10**6', '4.7*10**6', '3.3*10**6', '40*10**6', '7.8*10**6',
       '8.8*10**6', '6.6*10**6', '5.1*10**6', '61*10**6', '66*10**6',
       '79*10**3', '8.4*10**6', '3.7*10**6', '118*10**3', '44*10**6',
       '695*10**3', '1.6*10**6', '6.2*10**6', '53*10**6', '1.4*10**6',
       '3.0*10**6', '7.2*10**6', '5.8*10**6', '3.8*10**6', '9.6*10**6',
       '45*10**6', '63*10**6', '49*10**6', '77*10**6', '4.4*10**6',
       '70*10**6', '9.3*10**6', '8.1*10**6', '36*10**6', '6.9*10**6',
       '7.4*10**6', '84*10**6', '97*10**6', '2.0*10**6', '1.9*10**6',
       '1.8*10**6', '5.3*10**6', '47*10**6', '556*10**3', '526*10**3',
       '76*10**6', '7.6*10**6', '59*10**6', '9.7*10**6', '78*10**6',
       '72*10**6', '43*10**6', '7.7*10**6', '6.3*10**6', '334*10**3',
       '93*10**6', '65*10**6', '79*10**6', '100*10**6', '58*10**6',
       '50*10**6', '68*10**6', '64*10**6', '34*10**6', '67*10**6',
       '60*10**6', '94*10**6', '9.9*10**6', '232*10**3', '99*10**6',
       '624*10**3', '95*10**6', '8.5*10**3', '41*10**3', '292*10**3',
       '11*10**3', '80*10**6', '1.7*10**6', '10.0*10**6', '74*10**6',
       '62*10**6', '69*10**6', '75*10**6', '98*10**6', '85*10**6',
       '82*10**6', '96*10**6', '87*10**6', '71*10**6', '86*10**6',
       '91*10**6', '81*10**6', '92*10**6', '83*10**6', '88*10**6',
       '704*10**3', '862*10**3', '899*10**3', '378*10**3', '4.8*10**6',
       '266*10**3', '375*10**3', '1.3*10**6', '975*10**3', '980*10**3',
       '4.1*10**6', '89*10**6', '696*10**3', '544*10**3', '525*10**3',
       '920*10**3', '779*10**3', '853*10**3', '720*10**3', '713*10**3',
       '772*10**3', '318*10**3', '58*10**3', '241*10**3', '196*10**3',
       '857*10**3', '51*10**3', '953*10**3', '865*10**3', '251*10**3',
       '930*10**3', '540*10**3', '313*10**3', '746*10**3', '203*10**3',
       '26*10**3', '314*10**3', '239*10**3', '371*10**3', '220*10**3',
       '730*10**3', '756*10**3', '91*10**3', '293*10**3', '17*10**3',
       '74*10**3', '14*10**3', '317*10**3', '78*10**3', '924*10**3',
       '818*10**3', '81*10**3', '939*10**3', '169*10**3', '45*10**3',
       '965*10**3', '90*10**6', '545*10**3', '61*10**3', '283*10**3',
       '655*10**3', '714*10**3', '93*10**3', '872*10**3', '121*10**3',
       '322*10**3', '976*10**3', '206*10**3', '954*10**3', '444*10**3',
       '717*10**3', '210*10**3', '609*10**3', '308*10**3', '306*10**3',
       '175*10**3', '350*10**3', '383*10**3', '454*10**3', '1.0*10**6',
       '70*10**3', '812*10**3', '442*10**3', '842*10**3', '417*10**3',
       '412*10**3', '459*10**3', '478*10**3', '335*10**3', '782*10**3',
       '721*10**3', '430*10**3', '429*10**3', '192*10**3', '460*10**3',
       '728*10**3', '496*10**3', '816*10**3', '414*10**3', '506*10**3',
       '887*10**3', '613*10**3', '778*10**3', '683*10**3', '592*10**3',
       '186*10**3', '840*10**3', '647*10**3', '373*10**3', '437*10**3',
       '598*10**3', '716*10**3', '585*10**3', '982*10**3', '219*10**3',
       '55*10**3', '323*10**3', '691*10**3', '511*10**3', '951*10**3',
       '963*10**3', '25*10**3', '554*10**3', '351*10**3', '27*10**3',
       '82*10**3', '208*10**3', '551*10**3', '29*10**3', '103*10**3',
       '116*10**3', '153*10**3', '209*10**3', '499*10**3', '173*10**3',
       '597*10**3', '809*10**3', '122*10**3', '411*10**3', '400*10**3',
       '801*10**3', '787*10**3', '50*10**3', '643*10**3', '986*10**3',
       '516*10**3', '837*10**3', '780*10**3', '20*10**3', '498*10**3',
       '600*10**3', '656*10**3', '221*10**3', '228*10**3', '176*10**3',
       '34*10**3', '259*10**3', '164*10**3', '458*10**3', '629*10**3',
       '28*10**3', '288*10**3', '775*10**3', '785*10**3', '636*10**3',
       '916*10**3', '994*10**3', '309*10**3', '485*10**3', '914*10**3',
       '903*10**3', '608*10**3', '500*10**3', '54*10**3', '562*10**3',
       '847*10**3', '948*10**3', '811*10**3', '270*10**3', '48*10**3',
       '523*10**3', '784*10**3', '280*10**3', '24*10**3', '892*10**3',
       '154*10**3', '18*10**3', '33*10**3', '860*10**3', '364*10**3',
       '387*10**3', '626*10**3', '161*10**3', '879*10**3', '39*10**3',
       '170*10**3', '141*10**3', '160*10**3', '144*10**3', '143*10**3',
       '190*10**3', '376*10**3', '193*10**3', '473*10**3', '246*10**3',
       '73*10**3', '253*10**3', '957*10**3', '420*10**3', '72*10**3',
       '404*10**3', '470*10**3', '226*10**3', '240*10**3', '89*10**3',
       '234*10**3', '257*10**3', '861*10**3', '467*10**3', '676*10**3',
       '552*10**3', '582*10**3', '619*10**3'], dtype=object)


df['Size']=df['Size'][df['Size'].isnull()==False].map(eval)


df['Size'].unique()

array([1.90e+07, 1.40e+07, 8.70e+06, 2.50e+07, 2.80e+06, 5.60e+06,
       2.90e+07, 3.30e+07, 3.10e+06, 2.80e+07, 1.20e+07, 2.00e+07,
       2.10e+07, 3.70e+07, 2.70e+06, 5.50e+06, 1.70e+07, 3.90e+07,
       3.10e+07, 4.20e+06, 2.30e+07, 6.00e+06, 6.10e+06, 4.60e+06,
       9.20e+06, 5.20e+06, 1.10e+07, 2.40e+07,      nan, 9.40e+06,
       1.50e+07, 1.00e+07, 1.20e+06, 2.60e+07, 8.00e+06, 7.90e+06,
       5.60e+07, 5.70e+07, 3.50e+07, 5.40e+07, 2.01e+05, 3.60e+06,
       5.70e+06, 8.60e+06, 2.40e+06, 2.70e+07, 2.50e+06, 7.00e+06,
       1.60e+07, 3.40e+06, 8.90e+06, 3.90e+06, 2.90e+06, 3.80e+07,
       3.20e+07, 5.40e+06, 1.80e+07, 1.10e+06, 2.20e+06, 4.50e+06,
       9.80e+06, 5.20e+07, 9.00e+06, 6.70e+06, 3.00e+07, 2.60e+06,
       7.10e+06, 2.20e+07, 6.40e+06, 3.20e+06, 8.20e+06, 4.90e+06,
       9.50e+06, 5.00e+06, 5.90e+06, 1.30e+07, 7.30e+07, 6.80e+06,
       3.50e+06, 4.00e+06, 2.30e+06, 2.10e+06, 4.20e+07, 9.10e+06,
       5.50e+07, 2.30e+04, 7.30e+06, 6.50e+06, 1.50e+06, 7.50e+06,
       5.10e+07, 4.10e+07, 4.80e+07, 8.50e+06, 4.60e+07, 8.30e+06,
       4.30e+06, 4.70e+06, 3.30e+06, 4.00e+07, 7.80e+06, 8.80e+06,
       6.60e+06, 5.10e+06, 6.10e+07, 6.60e+07, 7.90e+04, 8.40e+06,
       3.70e+06, 1.18e+05, 4.40e+07, 6.95e+05, 1.60e+06, 6.20e+06,
       5.30e+07, 1.40e+06, 3.00e+06, 7.20e+06, 5.80e+06, 3.80e+06,
       9.60e+06, 4.50e+07, 6.30e+07, 4.90e+07, 7.70e+07, 4.40e+06,
       7.00e+07, 9.30e+06, 8.10e+06, 3.60e+07, 6.90e+06, 7.40e+06,
       8.40e+07, 9.70e+07, 2.00e+06, 1.90e+06, 1.80e+06, 5.30e+06,
       4.70e+07, 5.56e+05, 5.26e+05, 7.60e+07, 7.60e+06, 5.90e+07,
       9.70e+06, 7.80e+07, 7.20e+07, 4.30e+07, 7.70e+06, 6.30e+06,
       3.34e+05, 9.30e+07, 6.50e+07, 7.90e+07, 1.00e+08, 5.80e+07,
       5.00e+07, 6.80e+07, 6.40e+07, 3.40e+07, 6.70e+07, 6.00e+07,
       9.40e+07, 9.90e+06, 2.32e+05, 9.90e+07, 6.24e+05, 9.50e+07,
       8.50e+03, 4.10e+04, 2.92e+05, 1.10e+04, 8.00e+07, 1.70e+06,
       7.40e+07, 6.20e+07, 6.90e+07, 7.50e+07, 9.80e+07, 8.50e+07,
       8.20e+07, 9.60e+07, 8.70e+07, 7.10e+07, 8.60e+07, 9.10e+07,
       8.10e+07, 9.20e+07, 8.30e+07, 8.80e+07, 7.04e+05, 8.62e+05,
       8.99e+05, 3.78e+05, 4.80e+06, 2.66e+05, 3.75e+05, 1.30e+06,
       9.75e+05, 9.80e+05, 4.10e+06, 8.90e+07, 6.96e+05, 5.44e+05,
       5.25e+05, 9.20e+05, 7.79e+05, 8.53e+05, 7.20e+05, 7.13e+05,
       7.72e+05, 3.18e+05, 5.80e+04, 2.41e+05, 1.96e+05, 8.57e+05,
       5.10e+04, 9.53e+05, 8.65e+05, 2.51e+05, 9.30e+05, 5.40e+05,
       3.13e+05, 7.46e+05, 2.03e+05, 2.60e+04, 3.14e+05, 2.39e+05,
       3.71e+05, 2.20e+05, 7.30e+05, 7.56e+05, 9.10e+04, 2.93e+05,
       1.70e+04, 7.40e+04, 1.40e+04, 3.17e+05, 7.80e+04, 9.24e+05,
       8.18e+05, 8.10e+04, 9.39e+05, 1.69e+05, 4.50e+04, 9.65e+05,
       9.00e+07, 5.45e+05, 6.10e+04, 2.83e+05, 6.55e+05, 7.14e+05,
       9.30e+04, 8.72e+05, 1.21e+05, 3.22e+05, 9.76e+05, 2.06e+05,
       9.54e+05, 4.44e+05, 7.17e+05, 2.10e+05, 6.09e+05, 3.08e+05,
       3.06e+05, 1.75e+05, 3.50e+05, 3.83e+05, 4.54e+05, 1.00e+06,
       7.00e+04, 8.12e+05, 4.42e+05, 8.42e+05, 4.17e+05, 4.12e+05,
       4.59e+05, 4.78e+05, 3.35e+05, 7.82e+05, 7.21e+05, 4.30e+05,
       4.29e+05, 1.92e+05, 4.60e+05, 7.28e+05, 4.96e+05, 8.16e+05,
       4.14e+05, 5.06e+05, 8.87e+05, 6.13e+05, 7.78e+05, 6.83e+05,
       5.92e+05, 1.86e+05, 8.40e+05, 6.47e+05, 3.73e+05, 4.37e+05,
       5.98e+05, 7.16e+05, 5.85e+05, 9.82e+05, 2.19e+05, 5.50e+04,
       3.23e+05, 6.91e+05, 5.11e+05, 9.51e+05, 9.63e+05, 2.50e+04,
       5.54e+05, 3.51e+05, 2.70e+04, 8.20e+04, 2.08e+05, 5.51e+05,
       2.90e+04, 1.03e+05, 1.16e+05, 1.53e+05, 2.09e+05, 4.99e+05,
       1.73e+05, 5.97e+05, 8.09e+05, 1.22e+05, 4.11e+05, 4.00e+05,
       8.01e+05, 7.87e+05, 5.00e+04, 6.43e+05, 9.86e+05, 5.16e+05,
       8.37e+05, 7.80e+05, 2.00e+04, 4.98e+05, 6.00e+05, 6.56e+05,
       2.21e+05, 2.28e+05, 1.76e+05, 3.40e+04, 2.59e+05, 1.64e+05,
       4.58e+05, 6.29e+05, 2.80e+04, 2.88e+05, 7.75e+05, 7.85e+05,
       6.36e+05, 9.16e+05, 9.94e+05, 3.09e+05, 4.85e+05, 9.14e+05,
       9.03e+05, 6.08e+05, 5.00e+05, 5.40e+04, 5.62e+05, 8.47e+05,
       9.48e+05, 8.11e+05, 2.70e+05, 4.80e+04, 5.23e+05, 7.84e+05,
       2.80e+05, 2.40e+04, 8.92e+05, 1.54e+05, 1.80e+04, 3.30e+04,
       8.60e+05, 3.64e+05, 3.87e+05, 6.26e+05, 1.61e+05, 8.79e+05,
       3.90e+04, 1.70e+05, 1.41e+05, 1.60e+05, 1.44e+05, 1.43e+05,
       1.90e+05, 3.76e+05, 1.93e+05, 4.73e+05, 2.46e+05, 7.30e+04,
       2.53e+05, 9.57e+05, 4.20e+05, 7.20e+04, 4.04e+05, 4.70e+05,
       2.26e+05, 2.40e+05, 8.90e+04, 2.34e+05, 2.57e+05, 8.61e+05,
       4.67e+05, 6.76e+05, 5.52e+05, 5.82e+05, 6.19e+05])


df['Size'].dtype

dtype('float64')


df['Size'].isnull().sum()

1468


df.dropna(subset='Size',inplace=True)


df['Installs'].unique()

array(['10,000+', '500,000+', '5,000,000+', '50,000,000+', '100,000+',
       '50,000+', '1,000,000+', '10,000,000+', '5,000+', '100,000,000+',
       '1,000+', '500,000,000+', '100+', '500+', '10+', '1,000,000,000+',
       '5+', '50+', '1+'], dtype=object)


df['Installs'].replace({',':''},regex=True,inplace = True)


df['Installs']=df['Installs'].str.replace("+","")


df['Installs'].unique()

array(['10000', '500000', '5000000', '50000000', '100000', '50000',
       '1000000', '10000000', '5000', '100000000', '1000', '500000000',
       '100', '500', '10', '1000000000', '5', '50', '1'], dtype=object)


df['Installs']=df['Installs'].astype('int')


df['Installs'].dtype

dtype('int32')

df


df['Price'].unique()

array(['0', '$4.99', '$6.99', '$7.99', '$3.99', '$5.99', '$2.99', '$1.99',
       '$9.99', '$0.99', '$9.00', '$5.49', '$10.00', '$24.99', '$11.99',
       '$79.99', '$16.99', '$14.99', '$29.99', '$12.99', '$3.49',
       '$10.99', '$7.49', '$1.50', '$19.99', '$15.99', '$33.99', '$39.99',
       '$2.49', '$4.49', '$1.70', '$1.49', '$3.88', '$399.99', '$17.99',
       '$400.00', '$3.02', '$1.76', '$4.84', '$4.77', '$1.61', '$1.59',
       '$6.49', '$1.29', '$299.99', '$379.99', '$37.99', '$18.99',
       '$389.99', '$8.49', '$1.75', '$14.00', '$2.00', '$3.08', '$2.59',
       '$19.40', '$15.46', '$8.99', '$3.04', '$13.99', '$4.29', '$3.28',
       '$4.60', '$1.00', '$2.90', '$1.97', '$2.56', '$1.20'], dtype=object)


df['Price']=df['Price'].str.replace("$",'')


df['Price']=df['Price'].astype(float)
df['Price'].dtypes

dtype('float64')


df['Price'].unique()

array([  0.  ,   4.99,   6.99,   7.99,   3.99,   5.99,   2.99,   1.99,
         9.99,   0.99,   9.  ,   5.49,  10.  ,  24.99,  11.99,  79.99,
        16.99,  14.99,  29.99,  12.99,   3.49,  10.99,   7.49,   1.5 ,
        19.99,  15.99,  33.99,  39.99,   2.49,   4.49,   1.7 ,   1.49,
         3.88, 399.99,  17.99, 400.  ,   3.02,   1.76,   4.84,   4.77,
         1.61,   1.59,   6.49,   1.29, 299.99, 379.99,  37.99,  18.99,
       389.99,   8.49,   1.75,  14.  ,   2.  ,   3.08,   2.59,  19.4 ,
        15.46,   8.99,   3.04,  13.99,   4.29,   3.28,   4.6 ,   1.  ,
         2.9 ,   1.97,   2.56,   1.2 ])


df.drop(columns=['Rating','Current Ver','Android Ver','Genres','Last Updated','App'],inplace=True)


df.columns

Index(['Category', 'Reviews', 'Size', 'Installs', 'Type', 'Price',
       'Content Rating', 'Rating_category'],
      dtype='object')

df


col=df.select_dtypes(include='object').columns
for i in col:
    print(i," : ")
    print(df[i].unique())

Category  : 
['ART_AND_DESIGN' 'AUTO_AND_VEHICLES' 'BEAUTY' 'BOOKS_AND_REFERENCE'
 'BUSINESS' 'COMICS' 'COMMUNICATION' 'DATING' 'EDUCATION' 'ENTERTAINMENT'
 'EVENTS' 'FINANCE' 'FOOD_AND_DRINK' 'HEALTH_AND_FITNESS' 'HOUSE_AND_HOME'
 'LIBRARIES_AND_DEMO' 'LIFESTYLE' 'GAME' 'FAMILY' 'MEDICAL' 'SOCIAL'
 'SHOPPING' 'PHOTOGRAPHY' 'SPORTS' 'TRAVEL_AND_LOCAL' 'TOOLS'
 'PERSONALIZATION' 'PRODUCTIVITY' 'PARENTING' 'WEATHER' 'VIDEO_PLAYERS'
 'NEWS_AND_MAGAZINES' 'MAPS_AND_NAVIGATION']
Type  : 
['Free' 'Paid']
Content Rating  : 
['Everyone' 'Teen' 'Everyone 10+' 'Mature 17+' 'Adults only 18+' 'Unrated']
Rating_category  : 
['High' 'Low']


le_col=['Category','Content Rating','Rating_category']
ohe_col=['Type']
from sklearn.preprocessing import LabelEncoder,OneHotEncoder
le=LabelEncoder()
for i in le_col:
    df[i]=le.fit_transform(df[i])


ohe=OneHotEncoder(sparse=False)
ohe_df=pd.DataFrame(ohe.fit_transform(df[ohe_col]))
ohe_df


a=ohe.categories_
a

[array(['Free', 'Paid'], dtype=object)]


ohe_df.columns=list(a[0])


ohe_df


df.reset_index(drop=True,inplace=True)


df_final=pd.concat((df,ohe_df),axis='columns',ignore_index=True)


df_final


df_final.columns=list(df.columns)+list(ohe_df.columns)


df_final


df_final.drop(columns=ohe_col,inplace=True)


df_final.columns

Index(['Category', 'Reviews', 'Size', 'Installs', 'Price', 'Content Rating',
       'Rating_category', 'Free', 'Paid'],
      dtype='object')


y=df['Rating_category']
X=df_final.drop(columns='Rating_category')

X

y

0       0
1       0
2       0
3       0
4       0
       ..
7419    0
7420    0
7421    0
7422    0
7423    0
Name: Rating_category, Length: 7424, dtype: int32


from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.25,random_state=555)
X_train


X_test


y_train

5331    0
7378    0
7369    0
3663    0
123     0
       ..
2628    0
1057    0
7145    0
4782    0
6554    0
Name: Rating_category, Length: 5568, dtype: int32


y_test

4515    0
7003    0
1767    0
2169    0
3420    0
       ..
4666    0
3662    0
6416    0
3232    0
5169    0
Name: Rating_category, Length: 1856, dtype: int32


X_train.shape,X_test.shape,y_train.shape,y_test.shape

((5568, 8), (1856, 8), (5568,), (1856,))


from sklearn.preprocessing import StandardScaler
scaler=StandardScaler()
scaler.fit_transform(X,y)

array([[-2.03766618, -0.69434673, -0.15992777, ..., -0.46322046,
         0.28202925, -0.28202925],
       [-2.03766618, -0.20638643, -0.37330014, ..., -0.46322046,
         0.28202925, -0.28202925],
       [-2.03766618,  1.01463714, -0.59947486, ..., -0.46322046,
         0.28202925, -0.28202925],
       ...,
       [-0.68621673, -1.07700695,  1.29100439, ..., -0.46322046,
         0.28202925, -0.28202925],
       [-0.68621673, -1.63383939, -0.81711468, ..., -0.46322046,
         0.28202925, -0.28202925],
       [ 0.17379656,  1.42544875, -0.15992777, ..., -0.46322046,
         0.28202925, -0.28202925]])

	Rating
count	9367.000000
mean	4.193338
std	0.537431
min	1.000000
25%	4.000000
50%	4.300000
75%	4.500000
max	19.000000

	App	Category	Rating	Reviews	Size	Installs	Type	Price	Content Rating	Genres	Last Updated	Current Ver	Android Ver
0	Photo Editor & Candy Camera & Grid & ScrapBook	ART_AND_DESIGN	4.1	159	19M	10,000+	Free	0	Everyone	Art & Design	January 7, 2018	1.0.0	4.0.3 and up
1	Coloring book moana	ART_AND_DESIGN	3.9	967	14M	500,000+	Free	0	Everyone	Art & Design;Pretend Play	January 15, 2018	2.0.0	4.0.3 and up
2	U Launcher Lite – FREE Live Cool Themes, Hide ...	ART_AND_DESIGN	4.7	87510	8.7M	5,000,000+	Free	0	Everyone	Art & Design	August 1, 2018	1.2.4	4.0.3 and up
3	Sketch - Draw & Paint	ART_AND_DESIGN	4.5	215644	25M	50,000,000+	Free	0	Teen	Art & Design	June 8, 2018	Varies with device	4.2 and up
4	Pixel Draw - Number Art Coloring Book	ART_AND_DESIGN	4.3	967	2.8M	100,000+	Free	0	Everyone	Art & Design;Creativity	June 20, 2018	1.1	4.4 and up
...	...	...	...	...	...	...	...	...	...	...	...	...	...
10836	Sya9a Maroc - FR	FAMILY	4.5	38	53M	5,000+	Free	0	Everyone	Education	July 25, 2017	1.48	4.1 and up
10837	Fr. Mike Schmitz Audio Teachings	FAMILY	5.0	4	3.6M	100+	Free	0	Everyone	Education	July 6, 2018	1.0	4.1 and up
10838	Parkinson Exercices FR	MEDICAL	NaN	3	9.5M	1,000+	Free	0	Everyone	Medical	January 20, 2017	1.0	2.2 and up
10839	The SCP Foundation DB fr nn5n	BOOKS_AND_REFERENCE	4.5	114	Varies with device	1,000+	Free	0	Mature 17+	Books & Reference	January 19, 2015	Varies with device	Varies with device
10840	iHoroscope - 2018 Daily Horoscope & Astrology	LIFESTYLE	4.5	398307	19M	10,000,000+	Free	0	Everyone	Lifestyle	July 25, 2018	Varies with device	Varies with device

	App	Category	Reviews	Size	Installs	Type	Price	Content Rating	Genres	Last Updated	Current Ver	Android Ver
count	10841	10841	10841	10841	10841	10840	10841	10840	10841	10841	10833	10838
unique	9660	34	6002	462	22	3	93	6	120	1378	2832	33
top	ROBLOX	FAMILY	0	Varies with device	1,000,000+	Free	0	Everyone	Tools	August 3, 2018	Varies with device	4.1 and up
freq	9	1972	596	1695	1579	10039	10040	8714	842	326	1459	2451

	App	Category	Rating	Reviews	Size	Installs	Type	Price	Content Rating	Genres	Last Updated	Current Ver	Android Ver	Rating_category
0	Photo Editor & Candy Camera & Grid & ScrapBook	ART_AND_DESIGN	4.1	5.075174	19000000.0	10000	Free	0	Everyone	Art & Design	January 7, 2018	1.0.0	4.0.3 and up	High
1	Coloring book moana	ART_AND_DESIGN	3.9	6.875232	14000000.0	500000	Free	0	Everyone	Art & Design;Pretend Play	January 15, 2018	2.0.0	4.0.3 and up	High
2	U Launcher Lite – FREE Live Cool Themes, Hide ...	ART_AND_DESIGN	4.7	11.379520	8700000.0	5000000	Free	0	Everyone	Art & Design	August 1, 2018	1.2.4	4.0.3 and up	High
3	Sketch - Draw & Paint	ART_AND_DESIGN	4.5	12.281389	25000000.0	50000000	Free	0	Teen	Art & Design	June 8, 2018	Varies with device	4.2 and up	High
4	Pixel Draw - Number Art Coloring Book	ART_AND_DESIGN	4.3	6.875232	2800000.0	100000	Free	0	Everyone	Art & Design;Creativity	June 20, 2018	1.1	4.4 and up	High
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
10833	Chemin (fr)	BOOKS_AND_REFERENCE	4.8	3.806662	619000.0	1000	Free	0	Everyone	Books & Reference	March 23, 2014	0.8	2.2 and up	High
10834	FR Calculator	FAMILY	4.0	2.079442	2600000.0	500	Free	0	Everyone	Education	June 18, 2017	1.0.0	4.1 and up	High
10836	Sya9a Maroc - FR	FAMILY	4.5	3.663562	53000000.0	5000	Free	0	Everyone	Education	July 25, 2017	1.48	4.1 and up	High
10837	Fr. Mike Schmitz Audio Teachings	FAMILY	5.0	1.609438	3600000.0	100	Free	0	Everyone	Education	July 6, 2018	1.0	4.1 and up	High
10840	iHoroscope - 2018 Daily Horoscope & Astrology	LIFESTYLE	4.5	12.894981	19000000.0	10000000	Free	0	Everyone	Lifestyle	July 25, 2018	Varies with device	Varies with device	High

	0	1
0	1.0	0.0
1	1.0	0.0
2	1.0	0.0
3	1.0	0.0
4	1.0	0.0
...	...	...
7419	1.0	0.0
7420	1.0	0.0
7421	1.0	0.0
7422	1.0	0.0
7423	1.0	0.0

	Category	Reviews	Size	Installs	Price	Content Rating	Free	Paid
5331	12	8.364275	24000000.0	50000	0.0	1	1.0	0.0
7378	25	2.890372	2400000.0	1000	0.0	1	1.0	0.0
7369	19	5.814131	676000.0	10000	0.0	1	1.0	0.0
3663	26	9.915811	47000000.0	5000000	0.0	1	1.0	0.0
123	3	11.412763	5900000.0	5000000	0.0	1	1.0	0.0
...	...	...	...	...	...	...	...	...
2628	6	9.644717	2200000.0	1000000	0.0	1	1.0	0.0
1057	14	10.999680	7800000.0	5000000	0.0	1	1.0	0.0
7145	14	12.677123	27000000.0	50000000	0.0	4	1.0	0.0
4782	27	1.791759	1800000.0	5	0.0	1	1.0	0.0
6554	14	13.174189	49000000.0	10000000	0.0	2	1.0	0.0

	Category	Reviews	Size	Installs	Price	Content Rating	Free	Paid
4515	11	7.547502	72000000.0	50000	0.0	1	1.0	0.0
7003	4	3.332205	18000000.0	5000	0.0	1	1.0	0.0
1767	26	10.477232	16000000.0	1000000	0.0	1	1.0	0.0
2169	25	8.701513	4300000.0	500000	0.0	1	1.0	0.0
3420	11	7.355641	35000000.0	50000	0.0	1	1.0	0.0
...	...	...	...	...	...	...	...	...
4666	11	6.242223	9800000.0	50000	0.0	1	1.0	0.0
3662	16	4.779123	72000000.0	50000	0.0	1	1.0	0.0
6416	11	8.187021	19000000.0	500000	0.0	1	1.0	0.0
3232	25	8.538563	1400000.0	500000	0.0	1	1.0	0.0
5169	21	2.079442	3400000.0	1000	0.0	2	1.0	0.0

EDA & Data Preprocessing on Google App Store Rating Dataset.¶